Towards Rigorous Explainability by Feature Attribution

arXiv:2604.22662v1 Announce Type: cross Abstract: Shapley values are a cornerstone of explainable AI, yet their proliferation into competing formulations has created a fragmented

arXiv:2605.21758v1 Announce Type: new Abstract: Explainable AI (XAI) methods identify which features are relevant to a model's predictions but often fail to clarify why certain

arXiv:2604.15371v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision

arXiv:2603.29361v1 Announce Type: new Abstract: Tree ensembles (TEs) find a multitude of practical applications. They represent one of the most general and accurate classes of

arXiv:2605.11687v1 Announce Type: new Abstract: Financial institutions increasingly require AI explanations that are persistent, cross-validated across methods, and

arXiv:2606.15273v1 Announce Type: new Abstract: Shapley value-based feature attribution methods face challenges in scenarios involving complex feature interactions and causal

arXiv:2608.12555v1 Announce Type: new Abstract: Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the

arXiv:2603.18015v1 Announce Type: cross Abstract: Although automated harmful content detection systems are frequently used to monitor online platforms, moderators and end users